---
library_name: gguf
tags:
- gguf
- llama.cpp
- lm-studio
- aether
- german
- english
- text-generation
license: apache-2.0
language:
- de
- en
---

# Aether 2.2 - GGUF

Pre-quantized GGUF binaries for **Aether 2.2**.

Trained with SFT (Supervised Fine-Tuning) and PEFT (LoRA) on a custom dataset using local NVIDIA RTX GPU acceleration, Aether 2.2 provides fast, light-weight, and accurate conversational text generation in German and English.

> 🔗 **Looking for the Base / LoRA Adapter?**
> If you want to use the Hugging Face Transformers PEFT adapter instead, check out the main repository:
> 👉 **[Maxilicious20/Aether-2.2](https://huggingface.co/Maxilicious20/Aether-2.2)**

---

## 📦 Available Files & Quantizations

Choose the right file depending on your system's VRAM/RAM and performance needs:

| Filename | Quantization | Quality | Size | Description / Recommendation |
| :--- | :--- | :--- | :--- | :--- |
| `aether_2_2_f16.gguf` | FP16 / F16 | Maximum | ~2.88 GB | Uncompressed full precision. Best quality. |
| `aether_2_2_q8_0.gguf` | Q8_0 | Very High | ~1.53 GB | Near-lossless quantization. Excellent balance of precision and speed. |
| `aether_2_2_q4_k_m.gguf` | Q4_K_M | Balanced | ~940 MB | **Recommended.** Best compromise between speed, size, and minimal quality loss. |

---

## 🚀 How to Run Locally

### 1. LM Studio
1. Open LM Studio.
2. Search for `Maxilicious20/Aether-2.2-GGUF` or paste the repository ID.
3. Download your preferred quantization (e.g., `aether_2_2_q4_k_m.gguf`).
4. Load the model and start chatting!

### 2. Ollama / llama.cpp
You can run the GGUF file directly using `llama.cpp`:
```bash
./llama-cli -m aether_2_2_q4_k_m.gguf -p "Hello Aether!" -n 256